Readability Extractor
Paste messy page HTML and get just the article — nav, ads, and clutter removed. Runs entirely in your browser, no upload, no sign-up.
Readability extractor
Paste the HTML of a cluttered web page and get back just the main article — the title and body — with navigation, sidebars, ads, and boilerplate stripped out. It's the same idea as a browser "reader mode," running locally in your browser; nothing is uploaded.
How it works
- Uses a Readability-style algorithm (a Rust port of Mozilla's Readability) to score the page's blocks and keep the densest, most article-like content.
- Choose text for clean readable plain text, or html for the cleaned article markup (keeps headings, paragraphs, links, etc.).
Good for
- Saving an article to read later without the clutter.
- Feeding clean article text into a summarizer, word counter, or notes app.
- Cleaning scraped page source down to the real content.
FAQ
Does it fetch the URL for me?
No — paste the page's HTML. (Use the web-fetch tool first if you need to retrieve a page, then pass its HTML here.)
Why do I get "no article content found in the HTML"?
The Readability scoring couldn't find a dense, article-like block to keep. That
happens on landing pages, search/index pages, and — most often — on JavaScript
apps whose raw source is mostly <script> tags with no rendered text. For a
JS-rendered page, copy the rendered DOM instead (dev-tools → right-click
<html> → Copy → Copy outerHTML) and paste that.
Should I pick text or html output?
text (the default) gives clean plain text with the article title on the first
line — ideal for feeding into a summarizer or word counter. html keeps the
cleaned article markup: the title as an <h1> plus the surviving headings,
paragraphs, links, and images — better when you want to re-publish or restyle the
article.
Is anything uploaded?
No. The extractor is compiled to WebAssembly and runs entirely in your browser tab.
Developer & Automation Access
Run it from the terminal
Same engine as this page, headless — via the gizza CLI:
gizza tool readability-extractor "<html>…paste the article page source…</html>"New to the CLI? Get gizza →
Open it by URL
Pre-fill and auto-run this tool with query parameters — the names match the API/CLI:
https://gizza.ai/tools/readability-extractor/?html=%3Chtml%3E%E2%80%A6paste%20the%20article%20page%20source%E2%80%A6%3C%2Fhtml%3E&format=textMachine-readable descriptor: tool.json — title + parameters JSON Schema for agents.